CN117095247A - Numerical control machining-based machining gesture operation optimization method, system and medium - Google Patents
Numerical control machining-based machining gesture operation optimization method, system and medium Download PDFInfo
- Publication number
- CN117095247A CN117095247A CN202311366325.7A CN202311366325A CN117095247A CN 117095247 A CN117095247 A CN 117095247A CN 202311366325 A CN202311366325 A CN 202311366325A CN 117095247 A CN117095247 A CN 117095247A
- Authority
- CN
- China
- Prior art keywords
- gesture
- feature
- machining
- data
- processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003754 machining Methods 0.000 title claims abstract description 146
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005457 optimization Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 244
- 238000003066 decision tree Methods 0.000 claims abstract description 33
- 238000000605 extraction Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 206010034719 Personality change Diseases 0.000 claims abstract description 8
- 230000009466 transformation Effects 0.000 claims description 42
- 239000013598 vector Substances 0.000 claims description 30
- 238000004088 simulation Methods 0.000 claims description 29
- 238000013145 classification model Methods 0.000 claims description 26
- 238000005516 engineering process Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000012806 monitoring device Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 238000005206 flow analysis Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims 1
- 206010063385 Intellectualisation Diseases 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 13
- 238000004364 calculation method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000012935 Averaging Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010191 image analysis Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 238000013256 Gubra-Amylin NASH model Methods 0.000 description 2
- 230000003042 antagnostic effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000013524 data verification Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0475—Generative networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/094—Adversarial learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a processing gesture operation optimization method, a system and a medium based on numerical control processing, wherein the processing gesture operation optimization method, the system and the medium are used for acquiring numerical control processing demand data and a historical processing image set, and carrying out part identification and gesture feature extraction on the historical processing image set to obtain historical part processing image features; performing attitude change analysis and attitude feature prediction based on the historical part processing image features and numerical control processing demand data, and performing feature generation by combining with a GAN-based image feature generation model to obtain simulated attitude features; constructing a gesture recognition model based on a decision tree; and extracting features from the real-time processed part key image set, importing the feature extracted feature into a gesture recognition model for real-time gesture recognition, and generating a processing regulation and control scheme based on a recognition result. According to the invention, the gesture recognition can be accurately and rapidly carried out on the parts in the numerical control machining process, the generation of the numerical control operation scheme and the regulation and control of the machining steps are carried out based on the recognition result, and the intellectualization and the high efficiency of the numerical control machining are realized.
Description
Technical Field
The invention relates to the field of image analysis, in particular to a processing gesture operation optimization method, system and medium based on numerical control processing.
Background
The computer numerical control machining is a method for machining by utilizing a computer-controlled numerical control machine tool, and is widely applied to the part manufacturing of various industries. The machine tool is controlled to cut along a specified path through a pre-written processing program, so that the workpiece is processed.
However, the method is limited by the traditional technology, and at present, in the numerical control machining process, the condition that the machining gesture of a part is difficult to automatically and intelligently identify exists, so that the machining is defective, and manual inspection is still needed, so that the numerical control machining efficiency and precision are greatly influenced. Therefore, a method for optimizing the operation of the machining gesture based on numerical control machining is needed.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a processing gesture operation optimization method, a system and a medium based on numerical control processing.
The first aspect of the invention provides a processing attitude operation optimization method based on numerical control processing, which comprises the following steps:
acquiring part processing video data in real time and acquiring key images based on a machine vision technology to obtain a key image set;
Acquiring numerical control machining demand data and a historical machining image set, and carrying out part identification and gesture feature extraction on the historical machining image set to obtain historical part machining image features;
performing attitude change analysis and attitude feature prediction based on the historical part processing image features and numerical control processing demand data, and performing feature generation by combining with a GAN-based image feature generation model to obtain simulated attitude features;
constructing a gesture recognition model based on a decision tree based on the historical part processing image features and the simulated gesture features;
and extracting features of the key image set, importing the key image set into a gesture recognition model for real-time gesture recognition, and generating a processing regulation and control scheme based on recognition results.
In this scheme, based on machine vision technique, acquire part processing video data in real time and carry out key image acquisition, obtain key image set, specifically be:
the method comprises the steps of monitoring part machining video in real time and obtaining part machining video data through a high-definition video monitoring device;
extracting key frames of the part processing video data to obtain a key image set;
and carrying out noise reduction, smoothing, enhancement and standardization pretreatment on the images of the key image set.
In this scheme, acquire numerical control processing demand data and historical processing image collection, will the identification and the gesture characteristic extraction of part are carried out to the historical processing image collection, obtain historical part processing image feature, specifically do:
acquiring a historical processing image set and corresponding numerical control processing demand data in a preset historical time period;
performing processing flow analysis based on the numerical control processing demand data to obtain a plurality of processing step information;
based on the processing step information, standard characteristic data corresponding to the processing gesture of the part are obtained from a system database;
each processing step information corresponds to one standard characteristic data;
target part area identification is carried out according to the historical processing image set, and part image data are obtained;
extracting attitude features from the part image data to obtain first attitude feature data;
classifying the first attitude feature data based on the processing steps according to the standard feature data to obtain second attitude feature data corresponding to a plurality of processing steps;
and integrating the data of all the second attitude characteristic data to form the historical part processing image characteristics.
In this scheme, the gesture change analysis and gesture feature prediction are performed based on the historical part processing image features and numerical control processing demand data, and feature generation is performed by combining with a GAN-based image feature generation model, so as to obtain simulated gesture features, which specifically are:
Respectively carrying out feature vectorization on standard feature data and second attitude feature data corresponding to one processing step to obtain a standard feature vector and a second feature vector;
performing transformation analysis between vectors according to the standard feature vector and the second feature vector, obtaining feature transformation parameters, and taking the feature transformation parameters as gesture feature transformation parameters;
analyzing all processing steps, and carrying out parameter integration on all obtained attitude characteristic transformation parameters to obtain attitude characteristic transformation parameter information.
In this scheme, based on historical parts processing image feature and numerical control processing demand data carry out gesture change analysis and gesture feature prediction, combine image feature generation model based on GAN to carry out feature generation, obtain simulation gesture feature, still include:
constructing a GAN-based image feature generation model;
building a generator and a discriminator based on the image feature generation model, and setting a loss function and an optimizer for the generation model;
the method comprises the steps of importing historical part machining image features serving as real data into a generator, importing attitude feature transformation parameter information into the generator and serving as feature generation parameters of the generator;
generating cyclic characteristic data based on the generator, importing the generated characteristic data into a discriminator to perform discrimination countermeasure training, and updating the generator and the discriminator based on an error back propagation algorithm;
Performing countermeasure training on the image feature generation model circularly until the generator and the discriminator reach Nash balance;
and generating simulation feature data with preset data quantity based on the image feature generation model, and taking the simulation feature data as simulation attitude features.
In the scheme, the gesture recognition model based on the decision tree is constructed based on the historical part processing image features and the simulation gesture features, and specifically comprises the following steps:
dividing the simulated gesture features of the preset data quantity into N groups of simulated gesture feature data;
acquiring M pieces of second gesture feature data corresponding to the historical processing image set;
constructing a gesture classification model based on a decision tree;
performing feature vectorization based on N groups of simulated gesture feature data to form N groups of feature vector data, and performing node judgment condition conversion based on a decision tree based on the N groups of feature vector data to obtain N judgment nodes;
performing feature vectorization according to the M second gesture feature data and performing node judgment condition conversion based on a decision tree to obtain M judgment nodes;
and taking the M judging nodes as root nodes and father nodes in the gesture classification model, taking the N judging nodes as leaf nodes in the gesture classification model, and carrying out node optimization on the gesture classification model based on a preset heuristic algorithm to form the gesture classification model with a complete decision tree structure.
In this scheme, the feature extraction is performed on the key image set and the key image set is imported into a gesture recognition model for real-time gesture recognition, and a processing regulation and control scheme is generated based on a recognition result, specifically:
acquiring a key image set corresponding to the part processing video data in real time;
performing region identification and extraction of the current part based on the key image set to obtain current part image data;
extracting the features of the current part image data based on the contours and textures to obtain current feature data;
importing the current characteristic data into a gesture recognition model to perform gesture recognition and classification to obtain gesture classification result information;
and judging whether the posture deviation of the current part meets the current processing requirement or not based on the posture classification result information, and if not, generating a processing regulation and control scheme based on the posture classification result information.
The second aspect of the present invention also provides a processing gesture operation optimization system based on numerical control processing, the system comprising: the processing attitude operation optimizing program based on the numerical control processing is executed by the processor and comprises the following steps:
Acquiring part processing video data in real time and acquiring key images based on a machine vision technology to obtain a key image set;
acquiring numerical control machining demand data and a historical machining image set, and carrying out part identification and gesture feature extraction on the historical machining image set to obtain historical part machining image features;
performing attitude change analysis and attitude feature prediction based on the historical part processing image features and numerical control processing demand data, and performing feature generation by combining with a GAN-based image feature generation model to obtain simulated attitude features;
constructing a gesture recognition model based on a decision tree based on the historical part processing image features and the simulated gesture features;
and extracting features of the key image set, importing the key image set into a gesture recognition model for real-time gesture recognition, and generating a processing regulation and control scheme based on recognition results.
In this scheme, based on machine vision technique, acquire part processing video data in real time and carry out key image acquisition, obtain key image set, specifically be:
the method comprises the steps of monitoring part machining video in real time and obtaining part machining video data through a high-definition video monitoring device;
extracting key frames of the part processing video data to obtain a key image set;
And carrying out noise reduction, smoothing, enhancement and standardization pretreatment on the images of the key image set.
The third aspect of the present invention also provides a computer readable storage medium, where the computer readable storage medium includes a processing posture operation optimization program based on numerical control processing, where the processing posture operation optimization program based on numerical control processing is executed by a processor, to implement the steps of the processing posture operation optimization method based on numerical control processing as described in any one of the above.
The invention discloses a processing gesture operation optimization method, a system and a medium based on numerical control processing, wherein the processing gesture operation optimization method, the system and the medium are used for acquiring numerical control processing demand data and a historical processing image set, and carrying out part identification and gesture feature extraction on the historical processing image set to obtain historical part processing image features; performing attitude change analysis and attitude feature prediction based on the historical part processing image features and numerical control processing demand data, and performing feature generation by combining with a GAN-based image feature generation model to obtain simulated attitude features; constructing a gesture recognition model based on a decision tree; and extracting features from the real-time processed part key image set, importing the feature extracted feature into a gesture recognition model for real-time gesture recognition, and generating a processing regulation and control scheme based on a recognition result. According to the invention, the gesture recognition can be accurately and rapidly carried out on the parts in the numerical control machining process, the generation of the numerical control operation scheme and the regulation and control of the machining steps are carried out based on the recognition result, and the intellectualization and the high efficiency of the numerical control machining are realized.
Drawings
FIG. 1 shows a flow chart of a numerical control machining-based machining gesture operation optimization method of the application;
FIG. 2 illustrates a key image set acquisition flow chart of the present application;
FIG. 3 shows a flow chart for acquiring attitude feature transformation parameter information according to the present application;
FIG. 4 shows a block diagram of a numerical control machining-based machining gesture operation optimization system of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow chart of a numerical control machining-based machining gesture operation optimization method of the application.
As shown in fig. 1, a first aspect of the present application provides a processing gesture operation optimization method based on numerical control processing, including:
S102, acquiring part processing video data in real time and acquiring key images based on a machine vision technology to obtain a key image set;
s104, acquiring numerical control machining demand data and a historical machining image set, and carrying out part identification and gesture feature extraction on the historical machining image set to obtain historical part machining image features;
s106, carrying out gesture change analysis and gesture feature prediction based on the historical part processing image features and numerical control processing demand data, and carrying out feature generation by combining with a GAN-based image feature generation model to obtain simulated gesture features;
s108, constructing a gesture recognition model based on a decision tree based on the historical part machining image features and the simulated gesture features;
s110, extracting features of the key image set, importing the key image set into a gesture recognition model for real-time gesture recognition, and generating a machining regulation scheme based on a recognition result.
Fig. 2 shows a key image set acquisition flow chart of the present invention.
According to the embodiment of the invention, based on the machine vision technology, part processing video data are acquired in real time and key image acquisition is performed to obtain a key image set, specifically:
s202, monitoring a part machining video in real time and acquiring part machining video data through a high-definition video monitoring device;
S204, extracting key frames of the part machining video data to obtain a key image set;
s206, carrying out noise reduction, smoothing, enhancement and standardization pretreatment on the images of the key image set.
It should be noted that, the noise reduction, smoothing, enhancement and standardization preprocessing can enhance the image characteristics of the preliminarily obtained image data, improve the subsequent image analysis efficiency, and the number of the high-definition video monitoring devices is at least one, and a plurality of high-definition video monitoring devices can be set according to the actual processing requirements so as to meet the multi-angle machine vision image analysis.
According to the embodiment of the invention, the numerical control machining demand data and the historical machining image set are obtained, the historical machining image set is subjected to part identification and gesture feature extraction, and the historical part machining image features are obtained, specifically:
acquiring a historical processing image set and corresponding numerical control processing demand data in a preset historical time period;
performing processing flow analysis based on the numerical control processing demand data to obtain a plurality of processing step information;
based on the processing step information, standard characteristic data corresponding to the processing gesture of the part are obtained from a system database;
each processing step information corresponds to one standard characteristic data;
Target part area identification is carried out according to the historical processing image set, and part image data are obtained;
extracting attitude features from the part image data to obtain first attitude feature data;
classifying the first attitude feature data based on the processing steps according to the standard feature data to obtain second attitude feature data corresponding to a plurality of processing steps;
and integrating the data of all the second attitude characteristic data to form the historical part processing image characteristics.
The standard feature data of the part processing posture is the existing feature data and is used for comparing the standard data with the collected real-time data, so that the posture feature data of the current part can be retrieved and classified more efficiently. The classification of the first posture feature data based on the processing step is specifically that the comparison and classification of the feature similarity of the first posture feature data and the standard feature data are carried out. The first pose feature data includes a plurality of second pose feature data, one processing step corresponding to each of the second pose feature data.
Fig. 3 shows a flow chart of the attitude feature transformation parameter information acquisition of the present invention.
According to the embodiment of the invention, the processing image features and numerical control processing demand data based on the historical parts are subjected to gesture change analysis and gesture feature prediction, and feature generation is performed by combining with a GAN-based image feature generation model, so as to obtain simulated gesture features, which are specifically as follows:
s302, carrying out feature vectorization on standard feature data and second attitude feature data corresponding to one processing step respectively to obtain a standard feature vector and a second feature vector;
s304, carrying out transformation analysis between vectors according to the standard feature vector and the second feature vector, obtaining feature transformation parameters, and taking the feature transformation parameters as gesture feature transformation parameters;
s306, analyzing all processing steps, and carrying out parameter integration on all obtained attitude characteristic transformation parameters to obtain attitude characteristic transformation parameter information.
It should be noted that, each processing step has corresponding processing step information, and also has corresponding standard feature data and second gesture feature data. Because the part processing characteristics of the historical part processing image have a certain deviation compared with the standard characteristics, and the deviation angle, the deviation azimuth and the deviation position of the gesture are related to the processing steps and the processing technology, the invention further vectorizes the historical processing image characteristics and the standard image characteristics in the form of characteristic vectors and calculates transformation process parameters, thereby being capable of more intelligently analyzing the transformation deviation process of the part gesture and the standard gesture in the historical part processing image characteristics, and the gesture characteristic transformation parameters can reflect the gesture difference degree of the two. The attitude feature transformation parameter information includes a plurality of attitude feature transformation parameters. The gesture feature transformation parameters can be applied to the feature data prediction generation of the subsequent GAN model to obtain more real simulated feature data for the judgment of the decision tree, so that the gesture classification capability of the decision tree is further improved.
According to an embodiment of the present invention, the performing gesture change analysis and gesture feature prediction based on the historical part processing image features and the numerical control processing demand data, and performing feature generation in combination with a GAN-based image feature generation model to obtain a simulated gesture feature, further includes:
constructing a GAN-based image feature generation model;
building a generator and a discriminator based on the image feature generation model, and setting a loss function and an optimizer for the generation model;
the method comprises the steps of importing historical part machining image features serving as real data into a generator, importing attitude feature transformation parameter information into the generator and serving as feature generation parameters of the generator;
generating cyclic characteristic data based on the generator, importing the generated characteristic data into a discriminator to perform discrimination countermeasure training, and updating the generator and the discriminator based on an error back propagation algorithm;
performing countermeasure training on the image feature generation model circularly until the generator and the discriminator reach Nash balance;
and generating simulation feature data with preset data quantity based on the image feature generation model, and taking the simulation feature data as simulation attitude features.
It should be noted that the GAN is an unsupervised deep learning model, i.e. the antagonistic neural network.
According to the embodiment of the invention, the gesture recognition model based on the decision tree is constructed based on the historical part processing image characteristics and the simulated gesture characteristics, and specifically comprises the following steps:
dividing the simulated gesture features of the preset data quantity into N groups of simulated gesture feature data;
acquiring M pieces of second gesture feature data corresponding to the historical processing image set;
constructing a gesture classification model based on a decision tree;
performing feature vectorization based on N groups of simulated gesture feature data to form N groups of feature vector data, and performing node judgment condition conversion based on a decision tree based on the N groups of feature vector data to obtain N judgment nodes;
performing feature vectorization according to the M second gesture feature data and performing node judgment condition conversion based on a decision tree to obtain M judgment nodes;
and taking the M judging nodes as root nodes and father nodes in the gesture classification model, taking the N judging nodes as leaf nodes in the gesture classification model, and carrying out node optimization on the gesture classification model based on a preset heuristic algorithm to form the gesture classification model with a complete decision tree structure.
It should be noted that, in the N sets of simulated gesture feature data, each set of data corresponds to feature data of one gesture. And M is the number of processing steps. The preset heuristic algorithm comprises ID3, C4.5 and the like. The M judging nodes are used as root nodes and father nodes in the gesture classification model, so that the model can rapidly identify the gesture of real-time feature data, and the N judging nodes are used as leaf nodes in the gesture classification model, so that rapid gesture feature deviation identification and classification can be further realized.
According to the embodiment of the invention, the key image set is subjected to feature extraction and is imported into a gesture recognition model for real-time gesture recognition, and a processing regulation and control scheme is generated based on a recognition result, specifically:
acquiring a key image set corresponding to the part processing video data in real time;
performing region identification and extraction of the current part based on the key image set to obtain current part image data;
extracting the features of the current part image data based on the contours and textures to obtain current feature data;
importing the current characteristic data into a gesture recognition model to perform gesture recognition and classification to obtain gesture classification result information;
and judging whether the posture deviation of the current part meets the current processing requirement or not based on the posture classification result information, and if not, generating a processing regulation and control scheme based on the posture classification result information.
The gesture classification result information includes information such as a processing step, gesture deviation, gesture rationality and the like of the part. The gesture classification model has rapid part gesture recognition and classification functions. The machining regulation and control scheme comprises part posture correction regulation and control, numerical control machining parameter regulation and control and machining step regulation and control, and is used for realizing intelligent real-time machining regulation and control and improving the intelligent degree of a numerical control machining process.
According to an embodiment of the present invention, further comprising:
acquiring a batch of part processing image data within a preset time period;
extracting the gesture features of the part machining image data to obtain current gesture feature data, and importing the current gesture feature data into a gesture recognition model to perform gesture recognition classification to obtain current gesture classification result information;
acquiring the average attitude deviation rate of a batch of parts according to the current attitude classification result information;
generating a model according to the image characteristics, generating simulation characteristic data of a second preset data quantity and marking the simulation characteristic data as second simulation gesture characteristic data;
performing feature similarity calculation and averaging based on standard Euclidean distance on the second simulated gesture feature data and the current gesture feature data to obtain average feature similarity;
if the average attitude deviation rate is larger than a first preset value and the average feature similarity is larger than a second preset value, judging that the parts in one batch have machining defects, and generating a maintenance scheme and an operation optimization scheme of the numerical control equipment based on machining information corresponding to the parts in one batch.
It should be noted that, if the average deviation ratio of the gesture is greater than the first preset value and the average similarity of the features is greater than the second preset value, it indicates that defects exist in the numerical control machining tool or the machining parameters, and in the subsequent machining process, the same machining defect problem occurs at a greater probability in the next batch of parts, and the problem is difficult to solve only by analyzing and adjusting the machining gesture, so that the numerical control machining tool needs to be replaced or trimmed in time, and the related machining parameters need to be adjusted. The part processing image data comprises video data of a plurality of part processing, wherein the video data are obtained by image extraction, the parts are parts in the same batch, and the video data are continuous processing processes of the parts in a preset time period. The current gesture classification result information comprises classification result information of all parts in a batch, and the average gesture deviation rate of all the parts can be obtained through the information. The second preset data amount is larger than the preset data amount.
When analyzing the part processing image data of one batch, the historical part processing image characteristics and numerical control processing requirement data required for constructing the image characteristic generation model are consistent with the parts of the one batch, so that the simulation characteristic data corresponding to the parts of the one batch can be predicted and generated and compared.
In the feature similarity calculation and the averaging of the second simulation gesture feature data and the current gesture feature data based on the standard Euclidean distance, specifically, the data of the current gesture feature data is divided, and the similarity calculation and the averaging calculation are respectively carried out on the current gesture feature data and the second simulation gesture feature data, wherein the dividing quantity is determined by the data quantity of the second simulation gesture feature data, and the larger the data quantity is, the larger the dividing quantity is.
According to the invention, the characteristic generation of the deviation gesture can be carried out through the image characteristic generation model, the generated second simulated gesture characteristic data is compared with the gesture characteristics of a certain current batch of parts, the average characteristic similarity is further analyzed, the average characteristic similarity can effectively reflect the standard reaching degree of the gesture of the current batch of parts, the larger the average characteristic similarity is, the larger the overall deviation of the gesture of the current batch of parts is represented, in addition, the secondary data verification is carried out through the average gesture deviation rate, if the average gesture deviation rate and the average characteristic similarity are both larger than the preset standard, the larger processing defects exist in the processing process of the batch, and the defect screening is needed in time.
The maintenance scheme and the operation optimization scheme of the numerical control equipment can be used for analyzing and regulating defects of the processing equipment in real time, so that the subsequent cost loss is effectively reduced, the numerical control processing equipment is maintained, and the intelligent level of numerical control processing is improved.
FIG. 4 shows a block diagram of a numerical control machining-based machining gesture operation optimization system of the present invention.
The second aspect of the present invention also provides a processing gesture operation optimization system 4 based on numerical control processing, the system comprising: the processing posture operation optimizing program based on the numerical control processing is implemented by the processor when executed, and comprises the following steps:
acquiring part processing video data in real time and acquiring key images based on a machine vision technology to obtain a key image set;
acquiring numerical control machining demand data and a historical machining image set, and carrying out part identification and gesture feature extraction on the historical machining image set to obtain historical part machining image features;
performing attitude change analysis and attitude feature prediction based on the historical part processing image features and numerical control processing demand data, and performing feature generation by combining with a GAN-based image feature generation model to obtain simulated attitude features;
Constructing a gesture recognition model based on a decision tree based on the historical part processing image features and the simulated gesture features;
and extracting features of the key image set, importing the key image set into a gesture recognition model for real-time gesture recognition, and generating a processing regulation and control scheme based on recognition results.
According to the embodiment of the invention, based on the machine vision technology, part processing video data are acquired in real time and key image acquisition is performed to obtain a key image set, specifically:
the method comprises the steps of monitoring part machining video in real time and obtaining part machining video data through a high-definition video monitoring device;
extracting key frames of the part processing video data to obtain a key image set;
and carrying out noise reduction, smoothing, enhancement and standardization pretreatment on the images of the key image set.
It should be noted that, the noise reduction, smoothing, enhancement and standardization preprocessing can enhance the image characteristics of the preliminarily obtained image data, improve the subsequent image analysis efficiency, and the number of the high-definition video monitoring devices is at least one, and a plurality of high-definition video monitoring devices can be set according to the actual processing requirements so as to meet the multi-angle machine vision image analysis.
According to the embodiment of the invention, the numerical control machining demand data and the historical machining image set are obtained, the historical machining image set is subjected to part identification and gesture feature extraction, and the historical part machining image features are obtained, specifically:
Acquiring a historical processing image set and corresponding numerical control processing demand data in a preset historical time period;
performing processing flow analysis based on the numerical control processing demand data to obtain a plurality of processing step information;
based on the processing step information, standard characteristic data corresponding to the processing gesture of the part are obtained from a system database;
each processing step information corresponds to one standard characteristic data;
target part area identification is carried out according to the historical processing image set, and part image data are obtained;
extracting attitude features from the part image data to obtain first attitude feature data;
classifying the first attitude feature data based on the processing steps according to the standard feature data to obtain second attitude feature data corresponding to a plurality of processing steps;
and integrating the data of all the second attitude characteristic data to form the historical part processing image characteristics.
The standard feature data of the part processing posture is the existing feature data and is used for comparing the standard data with the collected real-time data, so that the posture feature data of the current part can be retrieved and classified more efficiently. The classification of the first posture feature data based on the processing step is specifically that the comparison and classification of the feature similarity of the first posture feature data and the standard feature data are carried out. The first pose feature data includes a plurality of second pose feature data, one processing step corresponding to each of the second pose feature data.
According to the embodiment of the invention, the processing image features and numerical control processing demand data based on the historical parts are subjected to gesture change analysis and gesture feature prediction, and feature generation is performed by combining with a GAN-based image feature generation model, so as to obtain simulated gesture features, which are specifically as follows:
respectively carrying out feature vectorization on standard feature data and second attitude feature data corresponding to one processing step to obtain a standard feature vector and a second feature vector;
performing transformation analysis between vectors according to the standard feature vector and the second feature vector, obtaining feature transformation parameters, and taking the feature transformation parameters as gesture feature transformation parameters;
analyzing all processing steps, and carrying out parameter integration on all obtained attitude characteristic transformation parameters to obtain attitude characteristic transformation parameter information.
It should be noted that, each processing step has corresponding processing step information, and also has corresponding standard feature data and second gesture feature data. Because the part processing characteristics of the historical part processing image have a certain deviation compared with the standard characteristics, and the deviation angle, the deviation azimuth and the deviation position of the gesture are related to the processing steps and the processing technology, the invention further vectorizes the historical processing image characteristics and the standard image characteristics in the form of characteristic vectors and calculates transformation process parameters, thereby being capable of more intelligently analyzing the transformation deviation process of the part gesture and the standard gesture in the historical part processing image characteristics, and the gesture characteristic transformation parameters can reflect the gesture difference degree of the two. The attitude feature transformation parameter information includes a plurality of attitude feature transformation parameters. The gesture feature transformation parameters can be applied to the feature data prediction generation of the subsequent GAN model to obtain more real simulated feature data for the judgment of the decision tree, so that the gesture classification capability of the decision tree is further improved.
According to an embodiment of the present invention, the performing gesture change analysis and gesture feature prediction based on the historical part processing image features and the numerical control processing demand data, and performing feature generation in combination with a GAN-based image feature generation model to obtain a simulated gesture feature, further includes:
constructing a GAN-based image feature generation model;
building a generator and a discriminator based on the image feature generation model, and setting a loss function and an optimizer for the generation model;
the method comprises the steps of importing historical part machining image features serving as real data into a generator, importing attitude feature transformation parameter information into the generator and serving as feature generation parameters of the generator;
generating cyclic characteristic data based on the generator, importing the generated characteristic data into a discriminator to perform discrimination countermeasure training, and updating the generator and the discriminator based on an error back propagation algorithm;
performing countermeasure training on the image feature generation model circularly until the generator and the discriminator reach Nash balance;
and generating simulation feature data with preset data quantity based on the image feature generation model, and taking the simulation feature data as simulation attitude features.
It should be noted that the GAN is an unsupervised deep learning model, i.e. the antagonistic neural network.
According to the embodiment of the invention, the gesture recognition model based on the decision tree is constructed based on the historical part processing image characteristics and the simulated gesture characteristics, and specifically comprises the following steps:
dividing the simulated gesture features of the preset data quantity into N groups of simulated gesture feature data;
acquiring M pieces of second gesture feature data corresponding to the historical processing image set;
constructing a gesture classification model based on a decision tree;
performing feature vectorization based on N groups of simulated gesture feature data to form N groups of feature vector data, and performing node judgment condition conversion based on a decision tree based on the N groups of feature vector data to obtain N judgment nodes;
performing feature vectorization according to the M second gesture feature data and performing node judgment condition conversion based on a decision tree to obtain M judgment nodes;
and taking the M judging nodes as root nodes and father nodes in the gesture classification model, taking the N judging nodes as leaf nodes in the gesture classification model, and carrying out node optimization on the gesture classification model based on a preset heuristic algorithm to form the gesture classification model with a complete decision tree structure.
It should be noted that, in the N sets of simulated gesture feature data, each set of data corresponds to feature data of one gesture. And M is the number of processing steps. The preset heuristic algorithm comprises ID3, C4.5 and the like. The M judging nodes are used as root nodes and father nodes in the gesture classification model, so that the model can rapidly identify the gesture of real-time feature data, and the N judging nodes are used as leaf nodes in the gesture classification model, so that rapid gesture feature deviation identification and classification can be further realized.
According to the embodiment of the invention, the key image set is subjected to feature extraction and is imported into a gesture recognition model for real-time gesture recognition, and a processing regulation and control scheme is generated based on a recognition result, specifically:
acquiring a key image set corresponding to the part processing video data in real time;
performing region identification and extraction of the current part based on the key image set to obtain current part image data;
extracting the features of the current part image data based on the contours and textures to obtain current feature data;
importing the current characteristic data into a gesture recognition model to perform gesture recognition and classification to obtain gesture classification result information;
and judging whether the posture deviation of the current part meets the current processing requirement or not based on the posture classification result information, and if not, generating a processing regulation and control scheme based on the posture classification result information.
The gesture classification result information includes information such as a processing step, gesture deviation, gesture rationality and the like of the part. The gesture classification model has rapid part gesture recognition and classification functions. The machining regulation and control scheme comprises part posture correction regulation and control, numerical control machining parameter regulation and control and machining step regulation and control, and is used for realizing intelligent real-time machining regulation and control and improving the intelligent degree of a numerical control machining process.
According to an embodiment of the present invention, further comprising:
acquiring a batch of part processing image data within a preset time period;
extracting the gesture features of the part machining image data to obtain current gesture feature data, and importing the current gesture feature data into a gesture recognition model to perform gesture recognition classification to obtain current gesture classification result information;
acquiring the average attitude deviation rate of a batch of parts according to the current attitude classification result information;
generating a model according to the image characteristics, generating simulation characteristic data of a second preset data quantity and marking the simulation characteristic data as second simulation gesture characteristic data;
performing feature similarity calculation and averaging based on standard Euclidean distance on the second simulated gesture feature data and the current gesture feature data to obtain average feature similarity;
if the average attitude deviation rate is larger than a first preset value and the average feature similarity is larger than a second preset value, judging that the parts in one batch have machining defects, and generating a maintenance scheme and an operation optimization scheme of the numerical control equipment based on machining information corresponding to the parts in one batch.
It should be noted that, if the average deviation ratio of the gesture is greater than the first preset value and the average similarity of the features is greater than the second preset value, it indicates that defects exist in the numerical control machining tool or the machining parameters, and in the subsequent machining process, the same machining defect problem occurs at a greater probability in the next batch of parts, and the problem is difficult to solve only by analyzing and adjusting the machining gesture, so that the numerical control machining tool needs to be replaced or trimmed in time, and the related machining parameters need to be adjusted. The part processing image data comprises video data of a plurality of part processing, wherein the video data are obtained by image extraction, the parts are parts in the same batch, and the video data are continuous processing processes of the parts in a preset time period. The current gesture classification result information comprises classification result information of all parts in a batch, and the average gesture deviation rate of all the parts can be obtained through the information. The second preset data amount is larger than the preset data amount.
When analyzing the part processing image data of one batch, the historical part processing image characteristics and numerical control processing requirement data required for constructing the image characteristic generation model are consistent with the parts of the one batch, so that the simulation characteristic data corresponding to the parts of the one batch can be predicted and generated and compared.
In the feature similarity calculation and the averaging of the second simulation gesture feature data and the current gesture feature data based on the standard Euclidean distance, specifically, the data of the current gesture feature data is divided, and the similarity calculation and the averaging calculation are respectively carried out on the current gesture feature data and the second simulation gesture feature data, wherein the dividing quantity is determined by the data quantity of the second simulation gesture feature data, and the larger the data quantity is, the larger the dividing quantity is.
According to the invention, the characteristic generation of the deviation gesture can be carried out through the image characteristic generation model, the generated second simulated gesture characteristic data is compared with the gesture characteristics of a certain current batch of parts, the average characteristic similarity is further analyzed, the average characteristic similarity can effectively reflect the standard reaching degree of the gesture of the current batch of parts, the larger the average characteristic similarity is, the larger the overall deviation of the gesture of the current batch of parts is represented, in addition, the secondary data verification is carried out through the average gesture deviation rate, if the average gesture deviation rate and the average characteristic similarity are both larger than the preset standard, the larger processing defects exist in the processing process of the batch, and the defect screening is needed in time.
The maintenance scheme and the operation optimization scheme of the numerical control equipment can be used for analyzing and regulating defects of the processing equipment in real time, so that the subsequent cost loss is effectively reduced, the numerical control processing equipment is maintained, and the intelligent level of numerical control processing is improved.
The third aspect of the present invention also provides a computer readable storage medium, where the computer readable storage medium includes a processing posture operation optimization program based on numerical control processing, where the processing posture operation optimization program based on numerical control processing is executed by a processor, to implement the steps of the processing posture operation optimization method based on numerical control processing as described in any one of the above.
The invention discloses a processing gesture operation optimization method, a system and a medium based on numerical control processing, wherein the processing gesture operation optimization method, the system and the medium are used for acquiring numerical control processing demand data and a historical processing image set, and carrying out part identification and gesture feature extraction on the historical processing image set to obtain historical part processing image features; performing attitude change analysis and attitude feature prediction based on the historical part processing image features and numerical control processing demand data, and performing feature generation by combining with a GAN-based image feature generation model to obtain simulated attitude features; constructing a gesture recognition model based on a decision tree; and extracting features from the real-time processed part key image set, importing the feature extracted feature into a gesture recognition model for real-time gesture recognition, and generating a processing regulation and control scheme based on a recognition result. According to the invention, the gesture recognition can be accurately and rapidly carried out on the parts in the numerical control machining process, the generation of the numerical control operation scheme and the regulation and control of the machining steps are carried out based on the recognition result, and the intellectualization and the high efficiency of the numerical control machining are realized.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The numerical control machining-based machining gesture operation optimization method is characterized by comprising the following steps of:
acquiring part processing video data in real time and acquiring key images based on a machine vision technology to obtain a key image set;
acquiring numerical control machining demand data and a historical machining image set, and carrying out part identification and gesture feature extraction on the historical machining image set to obtain historical part machining image features;
performing attitude change analysis and attitude feature prediction based on the historical part processing image features and numerical control processing demand data, and performing feature generation by combining with a GAN-based image feature generation model to obtain simulated attitude features;
constructing a gesture recognition model based on a decision tree based on the historical part processing image features and the simulated gesture features;
And extracting features of the key image set, importing the key image set into a gesture recognition model for real-time gesture recognition, and generating a processing regulation and control scheme based on recognition results.
2. The numerical control machining-based machining gesture operation optimization method according to claim 1, wherein the machine vision technology is adopted to acquire part machining video data in real time and perform key image acquisition to obtain a key image set, specifically:
the method comprises the steps of monitoring part machining video in real time and obtaining part machining video data through a high-definition video monitoring device;
extracting key frames of the part processing video data to obtain a key image set;
and carrying out noise reduction, smoothing, enhancement and standardization pretreatment on the images of the key image set.
3. The numerical control machining-based machining gesture operation optimization method according to claim 1, wherein the acquiring numerical control machining demand data and a historical machining image set, and performing part identification and gesture feature extraction on the historical machining image set to obtain historical part machining image features comprises the following specific steps:
acquiring a historical processing image set and corresponding numerical control processing demand data in a preset historical time period;
Performing processing flow analysis based on the numerical control processing demand data to obtain a plurality of processing step information;
based on the processing step information, standard characteristic data corresponding to the processing gesture of the part are obtained from a system database;
each processing step information corresponds to one standard characteristic data;
target part area identification is carried out according to the historical processing image set, and part image data are obtained;
extracting attitude features from the part image data to obtain first attitude feature data;
classifying the first attitude feature data based on the processing steps according to the standard feature data to obtain second attitude feature data corresponding to a plurality of processing steps;
and integrating the data of all the second attitude characteristic data to form the historical part processing image characteristics.
4. The numerical control machining-based machining gesture operation optimization method according to claim 3, wherein the gesture change analysis and gesture feature prediction are performed based on the historical part machining image features and numerical control machining demand data, and feature generation is performed by combining a GAN-based image feature generation model, so as to obtain simulated gesture features, specifically:
Respectively carrying out feature vectorization on standard feature data and second attitude feature data corresponding to one processing step to obtain a standard feature vector and a second feature vector;
performing transformation analysis between vectors according to the standard feature vector and the second feature vector, obtaining feature transformation parameters, and taking the feature transformation parameters as gesture feature transformation parameters;
analyzing all processing steps, and carrying out parameter integration on all obtained attitude characteristic transformation parameters to obtain attitude characteristic transformation parameter information.
5. The method for optimizing operation of a machining gesture based on numerical control machining according to claim 4, wherein the performing gesture change analysis and gesture feature prediction based on the historical part machining image features and numerical control machining demand data and performing feature generation in combination with a GAN-based image feature generation model to obtain a simulated gesture feature, further comprises:
constructing a GAN-based image feature generation model;
building a generator and a discriminator based on the image feature generation model, and setting a loss function and an optimizer for the generation model;
the method comprises the steps of importing historical part machining image features serving as real data into a generator, importing attitude feature transformation parameter information into the generator and serving as feature generation parameters of the generator;
Generating cyclic characteristic data based on the generator, importing the generated characteristic data into a discriminator to perform discrimination countermeasure training, and updating the generator and the discriminator based on an error back propagation algorithm;
performing countermeasure training on the image feature generation model circularly until the generator and the discriminator reach Nash balance;
and generating simulation feature data with preset data quantity based on the image feature generation model, and taking the simulation feature data as simulation attitude features.
6. The numerical control machining-based machining gesture operation optimization method according to claim 5, wherein the construction of the gesture recognition model based on the decision tree based on the historical part machining image features and the simulation gesture features is specifically as follows:
dividing the simulated gesture features of the preset data quantity into N groups of simulated gesture feature data;
acquiring M pieces of second gesture feature data corresponding to the historical processing image set;
constructing a gesture classification model based on a decision tree;
performing feature vectorization based on N groups of simulated gesture feature data to form N groups of feature vector data, and performing node judgment condition conversion based on a decision tree based on the N groups of feature vector data to obtain N judgment nodes;
Performing feature vectorization according to the M second gesture feature data and performing node judgment condition conversion based on a decision tree to obtain M judgment nodes;
and taking the M judging nodes as root nodes and father nodes in the gesture classification model, taking the N judging nodes as leaf nodes in the gesture classification model, and carrying out node optimization on the gesture classification model based on a preset heuristic algorithm to form the gesture classification model with a complete decision tree structure.
7. The numerical control machining-based machining gesture operation optimization method according to claim 6, wherein the feature extraction is performed on the key image set and the key image set is imported into a gesture recognition model for real-time gesture recognition, and a machining regulation scheme is generated based on recognition results, specifically:
acquiring a key image set corresponding to the part processing video data in real time;
performing region identification and extraction of the current part based on the key image set to obtain current part image data;
extracting the features of the current part image data based on the contours and textures to obtain current feature data;
importing the current characteristic data into a gesture recognition model to perform gesture recognition and classification to obtain gesture classification result information;
And judging whether the posture deviation of the current part meets the current processing requirement or not based on the posture classification result information, and if not, generating a processing regulation and control scheme based on the posture classification result information.
8. A numerical control machining-based machining gesture operation optimization system, comprising: the processing attitude operation optimizing program based on the numerical control processing is executed by the processor and comprises the following steps:
acquiring part processing video data in real time and acquiring key images based on a machine vision technology to obtain a key image set;
acquiring numerical control machining demand data and a historical machining image set, and carrying out part identification and gesture feature extraction on the historical machining image set to obtain historical part machining image features;
performing attitude change analysis and attitude feature prediction based on the historical part processing image features and numerical control processing demand data, and performing feature generation by combining with a GAN-based image feature generation model to obtain simulated attitude features;
constructing a gesture recognition model based on a decision tree based on the historical part processing image features and the simulated gesture features;
And extracting features of the key image set, importing the key image set into a gesture recognition model for real-time gesture recognition, and generating a processing regulation and control scheme based on recognition results.
9. The numerical control machining-based machining gesture operation optimization system according to claim 8, wherein the machine vision technology is used for acquiring part machining video data in real time and acquiring key images to obtain a key image set, specifically:
the method comprises the steps of monitoring part machining video in real time and obtaining part machining video data through a high-definition video monitoring device;
extracting key frames of the part processing video data to obtain a key image set;
and carrying out noise reduction, smoothing, enhancement and standardization pretreatment on the images of the key image set.
10. A computer-readable storage medium, wherein a machining posture operation optimization program based on numerical control machining is included in the computer-readable storage medium, and the steps of the machining posture operation optimization method based on numerical control machining according to any one of claims 1 to 7 are implemented when the machining posture operation optimization program based on numerical control machining is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311366325.7A CN117095247B (en) | 2023-10-20 | 2023-10-20 | Numerical control machining-based machining gesture operation optimization method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311366325.7A CN117095247B (en) | 2023-10-20 | 2023-10-20 | Numerical control machining-based machining gesture operation optimization method, system and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117095247A true CN117095247A (en) | 2023-11-21 |
| CN117095247B CN117095247B (en) | 2023-12-26 |
Family
ID=88771975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311366325.7A Active CN117095247B (en) | 2023-10-20 | 2023-10-20 | Numerical control machining-based machining gesture operation optimization method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117095247B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117689999A (en) * | 2024-02-04 | 2024-03-12 | 宝鸡核力材料科技有限公司 | Method and system for realizing TC4 tape coiling process optimization |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120283862A1 (en) * | 2010-02-05 | 2012-11-08 | Yoichi Nonaka | Processing path generation method and device for same |
| CN111198538A (en) * | 2018-10-30 | 2020-05-26 | 发那科株式会社 | Machining condition setting device and three-dimensional laser machining system |
| CN114445734A (en) * | 2021-12-24 | 2022-05-06 | 广东三维家信息科技有限公司 | Workpiece edge sealing method and device, electronic equipment and storage medium |
| CN115993804A (en) * | 2023-03-24 | 2023-04-21 | 中科航迈数控软件(深圳)有限公司 | Cutter parameter adjustment method based on numerical control machine tool and related equipment |
| US20230166732A1 (en) * | 2021-11-30 | 2023-06-01 | Deere & Company | Work machine distance prediction and action control |
| CN116862913A (en) * | 2023-09-04 | 2023-10-10 | 深圳市鑫典金光电科技有限公司 | Machine vision-based defect detection method and system for composite nickel-copper heat dissipation bottom plate |
-
2023
- 2023-10-20 CN CN202311366325.7A patent/CN117095247B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120283862A1 (en) * | 2010-02-05 | 2012-11-08 | Yoichi Nonaka | Processing path generation method and device for same |
| CN111198538A (en) * | 2018-10-30 | 2020-05-26 | 发那科株式会社 | Machining condition setting device and three-dimensional laser machining system |
| US20230166732A1 (en) * | 2021-11-30 | 2023-06-01 | Deere & Company | Work machine distance prediction and action control |
| CN114445734A (en) * | 2021-12-24 | 2022-05-06 | 广东三维家信息科技有限公司 | Workpiece edge sealing method and device, electronic equipment and storage medium |
| CN115993804A (en) * | 2023-03-24 | 2023-04-21 | 中科航迈数控软件(深圳)有限公司 | Cutter parameter adjustment method based on numerical control machine tool and related equipment |
| CN116862913A (en) * | 2023-09-04 | 2023-10-10 | 深圳市鑫典金光电科技有限公司 | Machine vision-based defect detection method and system for composite nickel-copper heat dissipation bottom plate |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117689999A (en) * | 2024-02-04 | 2024-03-12 | 宝鸡核力材料科技有限公司 | Method and system for realizing TC4 tape coiling process optimization |
| CN117689999B (en) * | 2024-02-04 | 2024-05-07 | 宝鸡核力材料科技有限公司 | Method and system for realizing TC4 tape coiling process optimization |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117095247B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111369016B (en) | Image recognition-based on-site operation and maintenance method and system | |
| CN111353413A (en) | Low-missing-report-rate defect identification method for power transmission equipment | |
| CN109271958B (en) | Face age identification method and device | |
| CN111832608B (en) | Iron spectrum image multi-abrasive particle identification method based on single-stage detection model yolov3 | |
| CN117095247B (en) | Numerical control machining-based machining gesture operation optimization method, system and medium | |
| CN111970400B (en) | Crank call identification method and device | |
| CN116502468B (en) | Method and system for controlling cattle carcass segmentation robot based on machine vision | |
| CN116843955A (en) | Microorganism classification and identification method and system based on computer vision | |
| CN117608259B (en) | Control method and system for storage chip production equipment | |
| CN116931534B (en) | Embroidery product production control method and system based on Internet of Things | |
| CN116542956B (en) | Automatic detection method and system for fabric components and readable storage medium | |
| CN116776647A (en) | Performance prediction method and system for composite nickel-copper-aluminum heat dissipation bottom plate | |
| CN114936614B (en) | Operation risk identification method and system based on neural network | |
| CN108363738B (en) | Recommendation method for industrial equipment data analysis algorithm | |
| CN114385876B (en) | Model search space generation method, device and system | |
| CN115392710A (en) | Wind turbine generator operation decision method and system based on data filtering | |
| CN115883182A (en) | Method and system for improving network security situation element identification efficiency | |
| CN113989742A (en) | Nuclear power station plant pedestrian detection method based on multi-scale feature fusion | |
| CN117850216B (en) | Intelligent control method and system for acrylic lens production equipment | |
| CN117689999B (en) | Method and system for realizing TC4 tape coiling process optimization | |
| CN115001941B (en) | Method and device for determining communication network management faults | |
| CN118014373B (en) | Risk identification model based on data quality monitoring and construction method thereof | |
| CN118035923B (en) | Power grid wave recording abnormal signal identification method | |
| CN116842415B (en) | Remote monitoring method, system and medium for mirror surface electric discharge machine | |
| CN117350549B (en) | Distribution network voltage risk identification method, device and equipment considering output correlation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |